© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 971
    Prev
    Next
    INDEX
    Explanations

    the word "le" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertising
    -0.75
     Wooden
    -0.64
    jury
    -0.64
    acion
    -0.63
     Yug
    -0.61
    龍
    -0.60
     tabl
    -0.60
    juries
    -0.59
     Easy
    -0.58
    ECD
    -0.58
    POSITIVE LOGITS
    pires
    0.83
    ourced
    0.81
    ilion
    0.75
    ichick
    0.74
    conservancy
    0.71
    prot
    0.70
    annels
    0.69
    byss
    0.68
    umped
    0.67
    mia
    0.65
    Activations Density 0.108%

    No Known Activations